BadApex: Backdoor Attack Based on Adaptive Optimization Mechanism of Black-box Large Language Models
Previous insertion-based and paraphrase-based backdoors have achieved great success in attack efficacy, but they ignore the text quality and semantic consistency between poisoned and clean texts. Although recent studies introduce LLMs to generate poisoned texts and improve the stealthiness, semantic consistency, and text quality, their hand-crafted prompts rely on expert experiences, facing significant challenges in prompt adaptability and attack performance after defenses. In this paper, we propose a novel backdoor attack based on adaptive optimization mechanism of black-box large language models (BadApex), which leverages a black-box LLM to generate poisoned text through a refined prompt. Specifically, an Adaptive Optimization Mechanism is designed to refine an initial prompt iteratively using the generation and modification agents. The generation agent generates the poisoned text based on the initial prompt. Then the modification agent evaluates the quality of the poisoned text and refines a new prompt. After several iterations of the above process, the refined prompt is used to generate poisoned texts through LLMs. We conduct extensive experiments on three dataset with six backdoor attacks and two defenses. Extensive experimental results demonstrate that BadApex significantly outperforms state-of-the-art attacks. It improves prompt adaptability, semantic consistency, and text quality. Furthermore, when two defense methods are applied, the average attack success rate (ASR) still up to 96.75%.
Code (0)
등록된 구현이 없습니다.
Tasks
Backdoor AttackSimilar Papers 제목 키워드 기반
TooBadRL: Trigger Optimization to Boost Effectiveness of Backdoor Attacks on Deep Reinforcement Learning
Deep reinforcement learning (DRL) has achieved remarkable success in a wide range of sequential decision-making domains, including robotics, healthcare, smart grids, and finance. Recent research demonstrates that attacke…
Deep Reinforcement LearningSequential Decision MakingTowards Backdoor Stealthiness in Model Parameter Space
Recent research on backdoor stealthiness focuses mainly on indistinguishable triggers in input space and inseparable backdoor representations in feature space, aiming to circumvent backdoor defenses that examine these re…
backdoor defensemodelInjection, Attack and Erasure: Revocable Backdoor Attacks via Machine Unlearning
Backdoor attacks pose a persistent security risk to deep neural networks (DNNs) due to their stealth and durability. While recent research has explored leveraging model unlearning mechanisms to enhance backdoor concealme…
Bilevel OptimizationAdaptive Backdoor Attacks with Reasonable Constraints on Graph Neural Networks
Recent studies show that graph neural networks (GNNs) are vulnerable to backdoor attacks. Existing backdoor attacks against GNNs use fixed-pattern triggers and lack reasonable trigger constraints, overlooking individual …
Backdoor AttackGraph SimilarityFedBAP: Backdoor Defense via Benign Adversarial Perturbation in Federated Learning
Federated Learning (FL) enables collaborative model training while preserving data privacy, but it is highly vulnerable to backdoor attacks. Most existing defense methods in FL have limited effectiveness due to their neg…
Federated Learning